CtrlK
BlogDocsLog inGet started
Tessl Logo

pre-push-check

Run the full pre-push review pipeline — code review checks, self-review against CLAUDE.md, and a final report.

48

Quality

50%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/pre-push-check/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a functional pre-push review skill with a clear sequential workflow and a well-defined output report format. Its main weaknesses are the lack of explicit validation checkpoints between steps (e.g., what happens when `devflow check` fails?) and the review checklists in steps 3-4 being descriptive rather than providing concrete, executable checking mechanisms. The trailing `$ARGUMENTS` placeholder suggests incomplete templating.

Suggestions

Add explicit validation checkpoints after step 2 (e.g., 'If `devflow check` exits non-zero, stop and report failures before proceeding to self-review')

Make steps 3 and 4 more actionable by providing concrete grep/search commands (e.g., `grep -rn 'console.log' src/` or `grep -rn ': any' src/**/*.ts`) rather than just listing what to look for

Remove or replace the dangling `$ARGUMENTS` placeholder at the end, which appears to be an unresolved template variable

DimensionReasoningScore

Conciseness

The skill is mostly efficient but includes some unnecessary elaboration. The CLAUDE.md compliance checklist items (naming conventions, architectural patterns, etc.) are somewhat verbose and could be tightened. The common issues checklist in step 4 overlaps with what step 3 already covers. However, it doesn't over-explain basic concepts.

2 / 3

Actionability

Step 1 and 2 provide concrete commands (`git diff --stat`, `devflow check`), but steps 3 and 4 are review checklists without executable commands or concrete code examples for how to actually perform those checks. The report template in step 5 is a good concrete output format, but the self-review steps are more descriptive than executable.

2 / 3

Workflow Clarity

The steps are clearly sequenced and numbered, and step 6 provides a decision point (fix or push). However, there's no explicit validation/feedback loop — if `devflow check` fails, there's no retry guidance. The workflow doesn't specify what to do if step 2 fails before proceeding to step 3, and the error recovery path is only mentioned at the very end rather than at each checkpoint.

2 / 3

Progressive Disclosure

The content is reasonably well-structured with numbered steps and a report template section. However, for a skill of this length (~70 lines of content), some of the checklist content (steps 3 and 4) could be split into referenced files. There are no bundle files and no references to external documents, though the skill references `.devflow/checks/*.md` and `CLAUDE.md` which are project files rather than skill bundle files.

2 / 3

Total

8

/

12

Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description communicates the general purpose of the skill — running a pre-push review pipeline — but lacks explicit trigger guidance ('Use when...') and specific detail about what the code review checks entail. The mention of CLAUDE.md adds some distinctiveness, but the description would benefit from clearer trigger terms and a more explicit 'when to use' clause.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user is about to push code, asks for a pre-push check, or mentions reviewing changes before pushing to a remote.'

Include more natural trigger terms users might say, such as 'before pushing', 'git push', 'push review', 'pre-commit review', or 'check before push'.

Specify the concrete actions more clearly, e.g., 'Runs linting, test verification, and style checks against CLAUDE.md conventions' instead of the vague 'code review checks'.

DimensionReasoningScore

Specificity

Names the domain (pre-push review) and lists some actions (code review checks, self-review against CLAUDE.md, final report), but the actions are somewhat vague — 'code review checks' doesn't specify what kind of checks, and 'final report' is generic.

2 / 3

Completeness

Describes what it does (run the pre-push review pipeline with code review checks, self-review, and report), but lacks an explicit 'Use when...' clause specifying when Claude should select this skill.

2 / 3

Trigger Term Quality

Includes some relevant terms like 'pre-push', 'code review', 'CLAUDE.md', and 'review pipeline', but misses common user phrasings like 'before pushing', 'push review', 'check my code before push', or 'git push'.

2 / 3

Distinctiveness Conflict Risk

The 'pre-push' qualifier and mention of CLAUDE.md provide some distinctiveness, but 'code review checks' could overlap with general code review skills, and the description doesn't clearly carve out its unique niche.

2 / 3

Total

8

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
AndreJorgeLopes/devflow
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.